Integration of spatio-temporal information for motion detection by means of fuzzy reasoning

  • M. Barni
  • F. Bartolini
  • V. Cappellini
  • F. Lambardi
Poster Session B: Active Vision, Motion, Shape, Stereo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)

Abstract

In this paper a motion detection system based on fuzzy reasoning is presented. Each pixel of a frame of the sequence is attempted to be classified as belonging to one of four classes (moving, still, uncovered background, covered background). The classes are treated as fuzzy sets, and as such, they are characterized by membership functions. After an initialization step, the degree of membership of each pixel to each class is refined by the application of a reasoning module driven by a set of fuzzy rules. Such fuzzy rules are designed so that the spatio-temporal correlation of image sequences is exploited by integrating information extracted from a small spatio-temporal neighborhood. The proposed system results to be flexible, thanks to the use of the reasoning approach (rules can be easily changed), and robust, thanks to the use of fuzzy logic.

Keywords

Membership Function Fuzzy Rule Linguistic Variable Motion Detection Fuzzy Reasoning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    S.B. Chae, J.S. Kim and R.H. Park “Video coding by segmenting motion vectors and frame differences,” vol. 32, no. 4, Apr. 1993, pp. 870–876.Google Scholar
  2. 2.
    I. Distein, “A new technique for visual motion alarm,” Pattern Recognition Letter, vol. 8, no. 5, Dec. 1988, pp. 347–351.Google Scholar
  3. 3.
    P.G. Michalopoulos, “Vehicle detection video through image processing: the Autoscope system,” IEEE Transactions on Vehicular Technology, vol. 40, no. 1, Feb. 1991, pp. 21–28.Google Scholar
  4. 4.
    T. Terano, K. Asai and M. Sugeno, Fuzzy Systems Theory and its Applications, Academic Press Inc. 1992.Google Scholar
  5. 5.
    P. Iliev and L. Tsekov, “Motion detection using image histogram sequence analysis,” Signal Processing, vol. 30, no. 3, Feb. 1993, pp. 373–384.Google Scholar
  6. 6.
    K.P. Karmann, A. Von Brandt and R. Gerl, “Moving object segmentation based on adaptive reference images,” Proc. EUSIPCO-90., Barcelon, Sept. 18–21, 1990.Google Scholar
  7. 7.
    M.A. Vicencio, B. Qiu and M.G. Hartley, “Algorithms and architectures for the analysis of road-traffic movements,” Proc. 3rd Int. Conf. Image Proc. and Appl., Warwich, UK, July 1989.Google Scholar
  8. 8.
    R. Jain and H.H. Nagel, “On the analysis of accumulative difference pictures from image sequences of real world scenes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 1, no. 2, Apr. 1979, pp. 206–214.Google Scholar
  9. 9.
    P. Bouthemy and P. Lalande, “Recovery of moving object masks in an image sequence using local spatio-temporal contextual information,” Optical Engineering, vol. 32, no. 6, June 1993, pp. 1205–1212.Google Scholar
  10. 10.
    R. Jain, “Extraction of motion information from peripheral processes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 3, no. 5, Sept. 1981, pp. 489–503.Google Scholar
  11. 11.
    L. A. Zadeh, “Outline of a new approach to the analysis of complex systems and decision processes”, IEEE Trans. Syst. Man Cybern., vol.SMC-3, pp. 28–44, 1973.Google Scholar
  12. 12.
    D. Dubois and H. Prade, Possibility Theory: an Approach to Computerized Processing of Uncertainty, New York, Plenum Press, 1988.Google Scholar
  13. 13.
    C. C. Lee, “Fuzzy logic in control systems: fuzzy logic controller-Part I and II”, IEEE Trans. Syst. Man Cibern., vol.SMC-20, no.2, pp. 404–435, Mar./Apr. 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • M. Barni
    • 1
  • F. Bartolini
    • 1
  • V. Cappellini
    • 1
  • F. Lambardi
    • 1
  1. 1.Dipartimento di Ingegneria ElettronicaUniversità di FirenzeFirenze

Personalised recommendations